Uncensored video generation API

The models and what they cost

A 5-second clip on minimax-h3-max-turbo at 768p costs $0.35.

Make a clip

Any OpenAI client works with its base URL set to https://nokeep.ai/v1. Send sk-nokeep-test as the key to walk through the whole flow free.

import os
import time
from openai import OpenAI

client = OpenAI(
    base_url="https://nokeep.ai/v1",
    api_key=os.environ["NOKEEP_API_KEY"],
)

clip = client.videos.create(
    model="minimax-h3-max-turbo",
    prompt="Waves breaking on a rocky coast at dusk",
    seconds="5",
    size="1280x720",
)

while clip.status in ("queued", "in_progress"):
    time.sleep(5)
    clip = client.videos.retrieve(clip.id)

if clip.status == "completed":
    client.videos.download_content(clip.id).write_to_file("clip.mp4")

Every field and route is in the reference.

What uncensored means here

The host marks both models uncensored, and your prompt goes to them as you wrote it. Adult content is in scope, and adult prompts rendered on both in our checks on 6 November 2026. A host can still refuse, which is a 422 content_refused error that costs nothing.

Four hard limits stay: sexual content involving minors, sexual content of real people, mass-casualty harm and targeting a real person. A prompt that crosses one gets 422 hard_limit and costs nothing. The rules are in the terms and Hard limits.

Text to video only

These routes take a prompt and nothing else. A request with a first frame or reference picture is refused, which also rules out animating a photo of a real person.

What is kept

A finished clip waits on the model’s host for up to 23 hours, on a private tier that stores no prompts. It is deleted after its one download, or when you delete it. We never hold the file, and our row about a clip has no prompt in it. The clip’s routes have the details.